Why are AI code editors not continuously working?

Question

I am getting more and more baffled by the incompetency of AI code editor developers. Why not simply have a "janitor" always running in the background, doing exactly the right refactorings, ensuring clean, well-tested code etc.? It would help so much against the AI slop problem. And it would be so simple to implement: Just some intelligent prompting or even static and dynamic analysis to detect re-occurring patterns in code and execution paths.

icedchai · Accepted Answer

It's not the fault of the "code editor developers." The underlying technology, GenAI, is non-deterministic. When you add input that varies widely in quality (prompts, existing code) what you describe is actually quite difficult.

baobun · Answer

> And it would be so simple to implement: Just some intelligent prompting or even static and dynamic analysis to detect re-occurring patterns in code and execution paths.So just do it, then? Or are you just as incompentent yourself?

codingdave · Answer

> doing exactly the right refactoringsAre you aware of any LLM models that can do that?

Why are AI code editors not continuously working?

It's not the fault of the "code editor developers." The underlying technology, GenAI, is non-deterministic. When you add input that varies widely in quality (prompts, existing code) what you describe is actually quite difficult.

> And it would be so simple to implement: Just some intelligent prompting or even static and dynamic analysis to detect re-occurring patterns in code and execution paths.
So just do it, then? Or are you just as incompentent yourself?

> doing exactly the right refactorings
Are you aware of any LLM models that can do that?